Nooman Ben Khalifa

Finite element method simulations are foundational to forming process design, but their utility for machine learning is often limited by idealizations that create a gap with stochastic, real-world manufacturing conditions. This paper investigates the systematic integration of simulation-based knowledge into machine learning pipelines to bridge this gap. A structured review of 56 publications reveals systemic limitations in current research, which we classify as the reality, validation, and trust gaps. In response, this work formulates four research questions to address these gaps, examining them through use cases in forging, blanking, and deep drawing. The analysis demonstrates that the impact of simulation simplifications is highly task-dependent, requiring a tailored approach to model selection and data integration. This paper contributes to the methodological discourse by proposing a framework for simulation-informed machine learning. It argues for a shift in focus from maximizing physical realism to a “fitfor-purpose” approach, where simulation complexity is strategically aligned with the requirements of the downstream machine learning task. The paper outlines a path toward more robust, interpretable, and industrially transferable modeling strategies in forming technology.

Industrial sheet metal components often have complex geometries with both concave and convex features. For small batch sizes, such components can be manufactured by incremental sheet forming, using the pressure of an active medium underneath the workpiece to create the convex feature. However, the additional load superimposed by the pressure causes instability and renders the process more prone to failure, in particular to cracking of the workpiece. The reliability of the manufacturing process could be improved if the occurrence of failure were predictable and thus preventable. To achieve this goal, the trend of the forming forces and the change of the workpiece geometry prior to cracking are experimentally analyzed. Subsequently, the dataset obtained from the experiments is used to fit a model based on long short-term memory and on a sliding window approach. This model reliably predicts the probability of failure with an accuracy and recall of 0.97 and 0.89 respectively, demonstrating its potential for online monitoring of the manufacturing process.

Accumulative Roll Bonding (ARB) is a severe plastic deformation process typically used to produce ultra-fine-grained structures. This study investigates the feasibility of using the ARB process to recycle aluminum chips from an Al-Mg-Si alloy (AA6063). The chips were first compacted under a 200 kN hydraulic press and then directly hot-rolled at 550 °C without prior heat treatment to a final sheet thickness of 1.5 mm. Subsequent ARB cycles were then applied to achieve full consolidation. Mechanical properties were evaluated through tensile testing and microhardness measurements, while microstructure was characterized using Optical Microscopy and SEM-EBSD. These analyses revealed significant grain refinement and improved homogeneity with increasing ARB cycles. Mechanical testing showed that the ARB process substantially enhanced both tensile strength and hardness of the recycled AA6063 chips while maintaining good ductility. The best results were obtained after two ARB cycles, yielding an ultimate tensile strength (UTS) of 170 MPa and an elongation at rupture of 15.7%. The study conclusively demonstrates that the ARB process represents a viable and effective method for recycling aluminum chips. This approach not only significantly improves mechanical properties and microstructural characteristics but also offers environmental benefits by eliminating the energy-intensive melting stage.

Deep rolling has advantages to modify local residual stresses in AA2024 sheets. A previous study about deep rolling for tailoring residual stresses [1] is extended in order to examine the homogeneity of the residual stress field. For the experimental residual stress analysis, the incremental hole drilling method with electronic speckle pattern interferometry is used with two different drill diameters. A numerical evaluation scheme is applied to simulation results of an existing process model with the aim of mimicking the experimental analysis technique. The volume under the deep rolled surface is classified in three sections based on the history of the process. Comparisons between experimental and simulative results yield a number of observations: Deeper evaluation with higher driller diameter does not come at a price of higher in-plane averaging of spatial gradients. Simulating a number of paths lower than those of the experiments shows similar homogeneity of the simulatively and experimentally analyzed stress field. Stretching the evaluation scheme from cylindrical volumes to cubic volumes shows very good qualitative agreement and validates the choice of classification.

In this paper, the feasibility of an innovative solid-state recycling process for aluminum alloy AA6063 chips through direct rolling is studied, with the aim of offering an environmentally sustainable alternative to conventional recycling processes. Aluminum chips, produced by milling an AA6063 billet without the use of lubricants, were first compacted using a hydraulic press with a 200 kN load and subsequently heat-treated at 570 °C for 6 h. The compacted chips were directly hot-rolled through several successive passes at 490 °C. The bulk material underwent the same rolling schedule to allow comparison of the samples and assess the process, in terms of mechanical properties and microstructure. All the rolled samples were tested by tensile and microhardness tests, whereas the microstructure was observed by an optical microscope and the EBSD-SEM technique. The fracture surface of all tested samples was analyzed by SEM. Recycled samples exhibited good mechanical properties, comparable to those of the bulk material. In particular, the bulk material showed an ultimate tensile strength of 218 MPa, in contrast to 177 MPa for the recycled chips, and comparable elongation at break. This study demonstrates that direct rolling of compacted aluminum chips is both technically feasible and has environmental benefits, offering a promising approach for sustainable aluminum recycling in industrial applications within a circular economy framework.

-Study on the effects of tool design and process parameters on the robustness of deep drawing HEINZEL Christine, THIERY Sebastian, BEN KHALIFA Noomane [butt

Fluctuating process conditions, such as lubrication, can disturb the production process and lead to faulty components that have cracks or wrinkles. Real-time identification of process parameters can detect deviations in sheet forming operations and enable the process parameters to be adjusted. To increase process robustness, closed-loop control is often used to monitor and influence the material draw-in, which corresponds to the material flow and can be measured by camera systems inside the deep-drawing press. The aim of this work is to develop a control concept that can predict the optimum blank holder force by estimating the coefficient of friction based on the material draw-in of the last stroke. Using a cross-die geometry, it is shown how the material draw-in can be determined experimentally by means of a camera system and numerically by FE simulations. Finally, artificial neural network-based models are trained through simulations and are subsequently tested on a numerical case study in which the coefficient of friction is changed as a disturbance variable and must be compensated for. The widely applicable control concept has the potential to incorporate additional softsensors, for example to determine material properties, and other target variables, such as the punch force, into the optimization algorithm.

Metal matrix nanocomposites are attracting attention because of their great potential for improved mechanical properties or possible functionalization. These hybrid materials are often produced by casting processes, but they can also develop their property profile after hot working, e.g. by forging or extrusion. In this paper a commercial cast magnesium alloy AM60 is enriched with